21 results about "Surface geometry" patented technology

The application provides an intelligent visual detection method and device for component defects, which comprises the following steps: loading a light standard three-dimensional model corresponding to a target component from a backend server; synchronously collecting real-time image data and depth data of the component on a conveying mechanism or a clamping mechanism; generating a real-time point cloud model for describing surface geometric features of the component based on the real-time image data and the depth data; matching the real-time point cloud model with the light standard three-dimensional model to locate a point area of interest in a high-defect area of the component; spatially mapping and fusing texture features in the real-time image data and the depth data in the point area of interest; and identifying defects in the point area of interest of the component through a joint probability model. The application can realize high-speed and accurate defect detection of components without complex feature engineering, and greatly reduces the maintenance difficulty and implementation cost of the algorithm.

This invention relates to the field of image processing technology and discloses a method for target 3D reconstruction and automated model generation. The method includes: acquiring multi-view original point cloud data of the target object, and obtaining a simplified point cloud dataset through voxel filtering and downsampling; dividing the data into smooth regions and sharp edge feature sets based on curvature characteristics, performing smooth fitting and edge-preserving reconstruction respectively, and then generating a composite mesh model through vertex merging and mesh stitching; performing topological structure analysis on the model, detecting and optimizing non-manifold elements and topological holes to obtain an initial mesh model; parametrically mapping and automatically unfolding the texture of the model surface geometric manifold characteristics, and fusing and binding the unfolded texture map with the initial mesh model to finally complete the 3D reconstruction of the target object; this invention can improve the efficiency of target 3D reconstruction and automated model generation.

This invention relates to the field of defect detection technology, specifically a method and system for detecting defects in valve sealing surfaces. The method extracts the position coordinates, geometric contours, and depth parameters of each abnormal morphology region from the three-dimensional surface morphology data of the sealing surface of the valve under inspection; determines the theoretical sealing contact area of ​​the sealing surface in the valve-closed state and spatially maps it with the position coordinates of each abnormal morphology region to filter out the abnormal regions to be judged; calculates the effective contact surface geometry after elastic deformation of the sealing surface under working conditions; based on the depth parameters and effective contact surface geometry of each abnormal region to be judged, if it is determined that the abnormal region to be judged is not completely covered by the effective contact surface after elastic deformation compensation, then the abnormal region to be judged is marked as a functional defect region and the detection result is output; accurately determining whether the abnormal morphology regions on the sealing surface constitute functional defects affecting the sealing function improves the accuracy of valve sealing surface defect detection.

The application relates to the technical field of image recognition, and discloses a packaging box damage degree online detection method and system based on image recognition, which comprises the following steps: carrying out spatial phase unfolding on a package phase diagram to obtain an absolute phase distribution diagram; generating a surface geometric deformation phase diagram; carrying out spatial alignment on the surface geometric deformation phase diagram to obtain local three-dimensional point cloud data; taking points with a normal vector mutation exceeding a preset threshold value in the local three-dimensional point cloud data as potential damage edge points, and marking points with a maximum principal curvature and minimum principal curvature difference exceeding a preset threshold value as potential deformation points; taking the potential damage edge points as seed points and taking the potential deformation points as growth constraint conditions to iteratively grow in the local three-dimensional point cloud data, and clustering points with continuity and similar geometric mutation characteristics into a damage area; and outputting a damage judgment result according to geometric parameters of the damage area; and the application can improve the efficiency of the packaging box damage degree online detection based on image recognition.

A method for context-based insertion of a three-dimensional (3D) object into a photograph includes analyzing, by a machine-learning model, a scene of the photograph to determine contextual attributes of the scene. The method also includes selecting, based on the contextual attributes, a 3D asset from a set of 3D assets. The method further includes posing the 3D asset using geometric information determined from the scene such that the posed 3D asset conforms to one or more of perspective, orientation, or surface geometry of the photograph. The method also includes adding a 3D element contextually associated with the scene, the 3D element being selected and positioned in accordance with the contextual attributes. The method further includes generating an output photograph that comprises the posed 3D asset and the 3D elements integrated into the photograph.

The application provides a double-curvature fusion curved surface SLAM navigation method, a longitudinal and transverse double-direction curvature parameter is estimated in real time through double-IMU fusion, an extended information filtering framework containing a double-curvature kinematic model, a laser data curved surface projection compensation algorithm and a path double-curvature compensation algorithm are constructed, and the scheme can accurately depict the curved surface geometric constraint where the robot actually locates; the accumulation of the transverse positioning error is inhibited through online estimation and fusion of the transverse curvature parameter; the accurate description and compensation of the robot side slip effect are realized through the establishment of a kinematic model containing a double-curvature coupling term; the data distortion is eliminated and the environment perception accuracy is improved through the projection of the laser scanning data from a plane to the estimated curved surface; finally, the consistency of the control instruction and the curved surface geometry is ensured through the real-time geometric compensation of the planning path based on the double-curvature parameter, and the stability and trajectory tracking accuracy of the control system under the longitudinal and transverse curvature coupling effect are enhanced.

This invention relates to the field of precision inspection and discloses a defect detection method based on machine vision. The method includes: an illumination device projecting a modulated light field containing multiple modulation periods, wherein the spatial light intensity distribution is shifted at a preset speed between adjacent periods; a photoelectric detection array acquiring a time-varying light intensity sequence reflected from the material surface, the sequence containing the reflected light intensity values ​​of multiple sampling points within the corresponding period; extracting the transient change gradient of the reflected light intensity within adjacent periods for sampling points at the same physical coordinate position on the corresponding material surface; determining an intrinsic light intensity change threshold based on the shift speed and sampling frequency; and identifying sampling points whose transient change gradient exceeds the threshold as physical breakage defects. This invention utilizes the constraint law of the geometric continuity of the material surface on the optical response to achieve the physical separation of texture interference signals and defect abrupt change signals, thereby solving the problem of misjudgment in defect measurement under complex topological surfaces.

This paper discloses the automated application of context-based image editing and personalized visual photograph preferences using artificial intelligence. A method for context-based insertion of three-dimensional (3D) objects into a photograph includes: analyzing the scene of the photograph using a machine learning model to determine the scene's contextual properties. The method also includes: selecting 3D assets from a set of 3D assets based on the contextual properties. The method further includes: posing the 3D assets using geometric information determined from the scene such that the posed 3D assets conform to one or more of the photograph's viewpoint, orientation, or surface geometry. The method also includes: adding 3D elements associated with the scene context, which are selected and positioned according to the contextual properties. The method further includes: generating an output photograph that includes the posed 3D assets and the 3D elements integrated into the photograph.

The application discloses a crane anti-collision protection system and method, and solves the problem of low accuracy of anti-collision protection of a crane in the prior art, has the beneficial effect of accurately judging the size of an obstacle, and has the specific scheme as follows: a crane anti-collision protection system comprises a radar unit, the radar unit is installed at the front end of a crane trolley, the front of the radar unit faces the advancing direction of the crane, the axis of the radar unit is obliquely installed with the vertical direction, and the radar unit obtains surface geometric three-dimensional point cloud data of obstacles in the set range of the moving path of the crane; a processing unit is connected with the radar unit, the processing unit converts the three-dimensional point cloud data fed back by the radar unit into three-dimensional coordinate data; an alarm unit is connected with the processing unit, the processing unit detects whether there is a risk obstacle in the preset protection area in the three-dimensional coordinate data, and if there is a risk obstacle, the processing unit controls the alarm unit to send an alarm signal.

This invention discloses a method for controlling the uniformity of coating thickness in aluminum single-panel spraying, relating to the field of aluminum single-panel curved surface spraying technology. The method includes: constructing a set of historical triangular spraying regions based on historical three-dimensional data of the aluminum single-panel curved surface and calculating their surface geometric features; training a coating thickness analysis model by combining historical surface geometric features with spraying process parameters; acquiring real-time triangular regions and their surface geometric features during real-time spraying; inputting the real-time features and process parameters into the model to predict the real-time coating thickness; further predicting the coating thickness of the next area to be sprayed and calculating its deviation from the target thickness; generating process parameter adjustment instructions based on the deviation and the area's surface geometric features, and adjusting parameters such as spray gun speed and flow rate in real-time during spraying. This invention, by associating surface geometry and spraying process through a machine learning model, achieves accurate prediction and dynamic compensation control of coating thickness on complex curved surfaces, effectively improving coating uniformity.

In various examples, a deep three-dimensional (3D) conditional generative model is implemented that can synthesize high-resolution 3D shapes using simple guides, such as coarse voxels, point clouds, etc., by synthesizing implicit and explicit 3D representations into a hybrid 3D representation. The present approach can directly optimize the reconstructed surface, allowing for the synthesis of finer geometric details with fewer artifacts. The systems and methods described herein can use a deformable tetrahedral grid that encodes a discrete signed distance function (SDF) and a differentiable marching tetrahedral layer that converts the implicit SDF representation to an explicit surface mesh representation marching tetrahedra. This combination allows for joint optimization of surface geometry and topology, as well as the generation of a subdivided hierarchy using reconstruction and adversarial losses explicitly defined on the surface mesh.

A computer-implemented method for visualizing the appearance of at least two materials comprises obtaining a first set of appearance attributes, the appearance attributes in the first set being associated with a first material, the first set of appearance attributes comprising measured appearance attributes; obtaining a second set of appearance attributes, the appearance attributes in the second set being associated with a second material; and obtaining a geometric model of at least one virtual object, the geometric model defining a three-dimensional macroscopic surface geometry of the virtual object. The invention is characterized in that a third set of appearance attributes is synthesized from the first set of appearance attributes and the second set of appearance attributes, and a scene comprising the at least one virtual object is visualized using a display device, using the third set of appearance attributes, using the comparison set of appearance attributes and the geometric model, using the third set of appearance attributes to visualize a first portion of the at least one virtual object, and using the comparison set of appearance attributes to visualize a second portion of the at least one virtual object to allow a direct visual comparison of the first set of appearance attributes as modified by the second set of appearance attributes and the comparison set of appearance attributes.

A system for geometric surface characterization comprises a deformable permeable layer coupled to a mounting structure and an interface film, the interface film comprising: a deformable permeable layer interfaced to at least one side of an interfaced object; a first illumination source operably coupled to the deformable permeable layer using an illumination control layer, the illumination control layer configured to emit first illumination light into the deformable permeable layer in one or more known first illumination orientations relative to the deformable permeable layer such that at least a portion of the first illumination light interacts with the deformable permeable layer; a detector configured to detect light from within at least a portion of the deformable permeable layer; and a computing system configured to characterize the geometric profile of the surface of an object interfaced to the interface film using the determined surface orientation.

The present application relates to the field of precision detection, and discloses a flaw detection method based on machine vision, comprising: an illumination device projects a modulated light field containing multiple modulation periods, and the spatial light intensity distribution between adjacent periods is controlled to phase shift at a preset speed; a photoelectric detection array collects a time-varying light intensity sequence reflected by a material surface, the sequence contains the reflected light intensity values of multiple sampling points in the corresponding period, for the sampling points of the same physical coordinate position on the corresponding material surface, the transient change gradient of the reflected light intensity in adjacent periods is extracted; the intrinsic light intensity change threshold is determined according to the shift speed and the sampling frequency, and the sampling points whose transient change gradient exceeds the threshold are judged as physical fracture flaw points, the present application uses the constraint law of the geometric continuity of the material surface on the optical response to realize the physical separation of the texture interference signal and the flaw mutation signal, and further solves the misjudgment problem of flaw detection under a complex topological surface.

The present application relates to the field of geological disaster monitoring and warning and geotechnical engineering informatization, and discloses a kind of satellite InSAR and ground displacement joint restraint's slope digital twinborn self-update and early warning method, solve the existing slope monitoring technology There are problems such as difficult multi-source data fusion, stability analysis cannot dynamically update parameters and sliding surface geometry, lack of digital twinborn model self-update capability and single early warning index.The present application fuses satellite InSAR surface deformation, ground GNSS point deformation, deep profile deformation data under unified space-time and coordinate datum, realizes the real-time self-update of model by constructing twinborn model augmented state containing geotechnical parameters and sliding surface geometric parameters, combined with hierarchical consistency constraint objective function, then fuses static stability index of limit equilibrium method and dynamic deformation index of proxy model, forms comprehensive hierarchical early warning system considering static stability and dynamic deformation characteristics of slope.

This application provides a method and apparatus for solving the completed state of a sealed assembly, relating to the field of sealing component design technology. It includes: acquiring the geometric model of an elastic component and its mating components and constructing an initial assembly configuration; discretizing the sealed assembly system using finite element methods and setting integration points in the elastic component; during the assembly iteration process, determining the corresponding projection point based on the integration point and the component combination it contains, and calculating the contact force at the integration point by combining material parameters, the projection point position, and the surface geometry information of the mating components; and unifying the contact force and the internal elastic force generated by the elastic component under the current configuration into a unified force balance relationship for nonlinear iterative solution until a preset convergence condition is met, thereby obtaining the completed state of the sealed assembly. This application can stably solve the completed state of a sealed assembly even with initial geometric interference, and improves the convergence and computational stability of the assembly simulation by uniformly handling the contact force and internal elastic force.

The application relates to the technical fields of plastic mold manufacturing and detection, and discloses a plastic mold defect detection method and system. The method comprises the following steps: acquiring initial three-dimensional point cloud data of a mold surface, and extracting a target point cloud data set containing a potential high stress area; performing regional division according to point cloud density difference and surface geometric curvature, screening out a local area with abnormal deformation as a high stress area candidate part; extracting a target feature vector of the candidate part, calculating a point cloud distribution imbalance index, and dynamically adjusting a sampling density to obtain an equalized point cloud subset; comparing the equalized point cloud subset with historical normal injection data, calculating a local deformation trend index, and when the index exceeds a threshold value, optimizing parameters of a pre-built deformation prediction model; performing overall deformation prediction on the mold based on the optimized model, evaluating deformation sensitivity of key positions, determining whether defects are generated, and outputting a detection result, and the application improves the accuracy of plastic mold defect detection.

The application relates to the technical field of three-dimensional model rendering and display, in particular to a commodity rendering and display method and system based on a 3D model, which comprises the following steps: obtaining a three-dimensional point cloud and multi-angle images of commodities, and constructing an initial three-dimensional grid model; performing topological analysis on the model to obtain a basic contour line set and a curved surface partition, and synchronously calculating the material reflectivity of the images to obtain a basic material texture map layer; deducing surface reflection characteristics and performing micro-surface geometric modeling according to the above results; constructing a multi-level visual feature tree from a macroscopic to a microscopic level based on the above results; according to a preset display intention, activating a matched feature node subset from the feature tree, and generating a corresponding dynamic rendering pipeline configuration; performing real-time lighting and material coloring operation on the initial grid model according to the configuration, and frame-by-frame synthesizing and rendering a display image. The application realizes efficient and accurate three-dimensional rendering which is dynamically driven according to a display intention.

A multi-agent control system coordinates autonomous agents to efficiently search two-dimensional and three-dimensional surfaces for targets. The system employs a multi-phase decentralized control strategy including deployment, circle formation, and spiral search phases. During circle formation, agents use a distributed consensus-based auction algorithm with wind-aware or current-aware cost calculations to assign themselves to evenly-spaced angular positions around a mission center. Agents then execute search trajectories with adjacent passes spaced at twice the sensor footprint radius to ensure complete coverage without gaps or overlaps. For two-dimensional surfaces, trajectories follow Archimedean spirals proven optimal for targets with radially-symmetric probability distributions. For three-dimensional surfaces, trajectories follow geodesic coils that conform to surface geometry using geodesic distance fields and level-set projection. The system includes obstacle avoidance capabilities using best-gap selection. Applications include search and rescue, reconnaissance, environmental monitoring, and surveillance.

The invention discloses a drill rod thickened transition area quality detection method and system based on inner conical surface scanning, particularly relates to the technical field of precision measurement of complex inner surface geometrical morphology, and aims to solve the problem that in the prior art, accurate and comprehensive quality evaluation on a complex conical surface in a drill rod thickened transition area is difficult. A scanning device is placed in an inner hole of a drill rod for scanning so as to obtain complete point cloud data of an inner conical surface; processing the point cloud data to generate an inner conical surface three-dimensional data set; calculating microscopic geometrical morphological characteristics based on the data set and dividing a plurality of function evaluation sub-regions according to the microscopic geometrical morphological characteristics; performing signal transformation analysis on the local three-dimensional shape data of each sub-region to obtain a signal domain feature data set; extracting a characteristic parameter set representing the surface quality state; comparing the parameter set of each sub-region with a preset reference, and comprehensively judging whether the quality is qualified or not; fine quantitative evaluation of the geometric quality of the inner conical surface of the drill rod is realized, and the pertinence and reliability of detection are improved.